SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge

Surgical data science has seen rapid advancement due to the excellent performance of end-to-end deep neural networks (DNNs) for surgical video analysis. Despite their successes, end-to-end DNNs have been proven susceptible to even minor corruptions, substantially impairing the model's performance. This vulnerability has become a major concern for the translation of cutting-edge technology, especially for high-stakes decision-making in surgical data science. We introduce SegSTRONG-C, a benchmark and challenge in surgical data science dedicated, aiming to better understand model deterioration under unforeseen but plausible non-adversarial corruption and the capabilities of contemporary methods that seek to improve it. Through comprehensive baseline experiments and participating submissions from widespread community engagement, SegSTRONG-C reveals key themes for model failure and identifies promising directions for improving robustness. The performance of challenge winners, achieving an average 0.9394 DSC and 0.9301 NSD across the unreleased test sets with corruption types: bleeding, smoke, and low brightness, shows inspiring improvement of 0.1471 DSC and 0.2584 NSD in average comparing to strongest baseline methods with UNet architecture trained with AutoAugment. In conclusion, the SegSTRONG-C challenge has identified some practical approaches for enhancing model robustness, yet most approaches relied on conventional techniques that have known, and sometimes quite severe, limitations. Looking ahead, we advocate for expanding intellectual diversity and creativity in non-adversarial robustness beyond data augmentation or training scale, calling for new paradigms that enhance universal robustness to corruptions and may enable richer applications in surgical data science.

@article{ding2025_2407.11906,
  title={ SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge },
  author={ Hao Ding and Yuqian Zhang and Tuxun Lu and Ruixing Liang and Hongchao Shu and Lalithkumar Seenivasan and Yonghao Long and Qi Dou and Cong Gao and Yicheng Leng and Seok Bong Yoo and Eung-Joo Lee and Negin Ghamsarian and Klaus Schoeffmann and Raphael Sznitman and Zijian Wu and Yuxin Chen and Septimiu E. Salcudean and Samra Irshad and Shadi Albarqouni and Seong Tae Kim and Yueyi Sun and An Wang and Long Bai and Hongliang Ren and Ihsan Ullah and Ho-Gun Ha and Attaullah Khan and Hyunki Lee and Satoshi Kondo and Satoshi Kasai and Kousuke Hirasawa and Sita Tailor and Ricardo Sanchez-Matilla and Imanol Luengo and Tianhao Fu and Jun Ma and Bo Wang and Marcos Fernández-Rodríguez and Estevao Lima and João L. Vilaça and Mathias Unberath },
  journal={arXiv preprint arXiv:2407.11906},
  year={ 2025 }
}